CN105139340A - Method and device for splicing panoramic photos - Google Patents
Method and device for splicing panoramic photos Download PDFInfo
- Publication number
- CN105139340A CN105139340A CN201510585372.XA CN201510585372A CN105139340A CN 105139340 A CN105139340 A CN 105139340A CN 201510585372 A CN201510585372 A CN 201510585372A CN 105139340 A CN105139340 A CN 105139340A
- Authority
- CN
- China
- Prior art keywords
- image
- human face
- face region
- spliced
- field picture
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 43
- 230000001815 facial effect Effects 0.000 claims description 50
- 238000010586 diagram Methods 0.000 description 4
- 230000000694 effects Effects 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000008030 elimination Effects 0.000 description 1
- 238000003379 elimination reaction Methods 0.000 description 1
- 238000004091 panning Methods 0.000 description 1
- LENZDBCJOHFCAS-UHFFFAOYSA-N tris Chemical compound OCC(N)(CO)CO LENZDBCJOHFCAS-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06T—IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06T3/00—Geometric image transformations in the plane of the image
- G06T3/40—Scaling of whole images or parts thereof, e.g. expanding or contracting
- G06T3/4038—Image mosaicing, e.g. composing plane images from plane sub-images
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Studio Devices (AREA)
- Image Processing (AREA)
Abstract
The embodiment of the present invention discloses a method and device for splicing panoramic photos. The method for splicing panoramic photos comprises: when a face area is identified in a current image, it is determined whether the face area accords with the splicing condition; if the face area does not accord with the splicing condition, the face area is removed from the current image, and the current image to be spliced is obtained; if the face area accords with the splicing condition, the current image is determined to be the current image to be spliced; the current image to be spliced and the spliced image are spliced to form a new spliced image; and the current image is any one from a second frame image to the last one frame image obtained at the panorama shot. By employing the technical scheme of the embodiment provided by the invention, images except a first frame image are spliced in order, face areas in accord with the splicing condition are only reserved when splicing, therefore the face images contained in the spliced panoramic photos do not have distortion cases such as dislocation or twisting and the like, the user requirement of high quality face images in the panoramic photos may be satisfied, and the user experience is improved.
Description
Technical field
The embodiment of the present invention relates to technical field of image processing, particularly relates to a kind of joining method and device of distant view photograph.
Background technology
At present, the mobile terminals such as smart mobile phone, panel computer and digital camera are all built-in with panorama camera function, and the mobile phone users as amateur Camera crews is easily realized panning the hope of photo.
The existing panorama process of taking pictures is: after user enters panoramic photographing mode, triggering is taken pictures button, under the prompting of the mark such as the arrow in preview interface or straight line, move the mobile terminal in hand according to certain reference direction, the camera on mobile terminal is with the continuous shoot multi-frame images of certain frequency.Mobile terminal splices the multiple image of shooting successively according to shooting order, by splicing part and next frame image compare, parts different in next frame is spliced to splicing part and obtains new splicing part, until after having spliced last frame image, generate complete distant view photograph.When moving the mobile terminal in hand as user, there is shake possibly and depart from reference direction, causing the last distant view photograph generated that the distortion situations such as dislocation or distortion can occur.Especially when comprising face in photo, dislocation or the distortion of facial image can be caused, and user more wishes to obtain complete and distortionless facial image, so the distant view photograph effect of taking out according to existing distant view photograph connection scheme is unsatisfactory, cannot meet consumers' demand.
Summary of the invention
The object of the embodiment of the present invention is to provide a kind of joining method and device of distant view photograph, to solve the problem that existing distant view photograph connection scheme cannot avoid facial image distortion.
On the one hand, embodiments provide a kind of joining method of distant view photograph, comprising:
When recognize in present image comprise human face region time, judge whether described human face region meets splicing condition, if do not meet, then from described present image, remove described human face region, obtain current image to be spliced; If meet, then determine that described present image is current image to be spliced;
Described current image to be spliced and stitching image are spliced, forms new stitching image;
Wherein, the second two field picture obtained when described present image is pan-shot is to any one in last frame image.
On the other hand, embodiments provide a kind of splicing apparatus of distant view photograph, comprising:
Current image determination module to be spliced, for when recognize in present image comprise human face region time, judge whether described human face region meets splicing condition, if do not meet, then from described present image, remove described human face region, obtain current image to be spliced; If meet, then determine that described present image is current image to be spliced;
Concatenation module, for described current image to be spliced and stitching image being spliced, forms new stitching image;
Wherein, the second two field picture obtained when described present image is pan-shot is to any one in last frame image.
The connection scheme of the distant view photograph provided in the embodiment of the present invention, the second two field picture obtained during pan-shot all can be considered present image to any one in last frame image, when recognize in present image comprise human face region time, judge whether human face region meets splicing condition, if do not meet, then from present image, remove human face region, obtain current image to be spliced; If meet, then determine that present image is current image to be spliced; Current image to be spliced and stitching image are spliced, forms new stitching image.By adopting technique scheme, successively the image except the first two field picture is spliced, when splicing, only aperture is merged the human face region of the condition of connecing, thus ensure that the facial image comprised in the distant view photograph be spliced into can not exist the distortion situations such as dislocation or distortion, meet the high-quality demand of user to facial image in distant view photograph, promote Consumer's Experience.
Accompanying drawing explanation
The schematic flow sheet of the joining method of a kind of distant view photograph that Fig. 1 provides for the embodiment of the present invention one;
The human face region schematic diagram that Fig. 2 provides for the embodiment of the present invention one;
The schematic flow sheet of the joining method of a kind of distant view photograph that Fig. 3 provides for the embodiment of the present invention two;
The schematic flow sheet of the joining method of a kind of preferred distant view photograph that Fig. 4 provides for the embodiment of the present invention three;
The structured flowchart of the splicing apparatus of a kind of distant view photograph that Fig. 5 provides for the embodiment of the present invention four.
Embodiment
Technical scheme of the present invention is further illustrated by embodiment below in conjunction with accompanying drawing.Be understandable that, specific embodiment described herein is only for explaining the present invention, but not limitation of the invention.It also should be noted that, for convenience of description, illustrate only part related to the present invention in accompanying drawing but not entire infrastructure.
Before in further detail exemplary embodiment being discussed, it should be mentioned that some exemplary embodiments are described as the process or method described as process flow diagram.Although each step is described as the process of order by process flow diagram, many steps wherein can be implemented concurrently, concomitantly or simultaneously.In addition, the order of each step can be rearranged.Described process can be terminated when its operations are completed, but can also have the additional step do not comprised in the accompanying drawings.Described process can correspond to method, function, code, subroutine, subroutine etc.
Embodiment one
The schematic flow sheet of the joining method of a kind of distant view photograph that Fig. 1 provides for the embodiment of the present invention one, the method can be performed by the splicing apparatus of distant view photograph, and wherein this device can by software and/or hardware implementing, and general accessible site in the terminal.As shown in Figure 1, the method comprises:
Step 101, recognize in present image and comprise human face region.
Wherein, the second two field picture obtained when described present image is pan-shot is to any one in last frame image.
Exemplary, the mobile terminal in the embodiment of the present invention specifically can be the terminal that smart mobile phone, panel computer and digital camera etc. are built-in with panorama camera function.When user opens the pan-shot function of mobile terminal, camera on mobile terminal is taken continuously with certain frequency, make acquisition for mobile terminal to multiple image, the present image in the present embodiment is the second two field picture in this multiple image to any one in last frame image.
Exemplary, the human face region schematic diagram that Fig. 2 provides for the embodiment of the present invention one.Described human face region can be the region comprising part or all of facial image, can determine with reference to facial contour 201.Such as, in part face image-region 203, contain a part for facial contour 201, in whole facial image region 202, contain whole facial contours 201; Also can be the region comprising facial contour edge position images, facial contour 201 as contiguous in the face fringe region 204 in Fig. 2.The benefit of such setting is, the fringe region of facial contour 201 may comprise the image section closely-related with face such as hair, cap and various ornaments, can ensure that the distortion phenomenons such as dislocation or distortion can not occur whole head image.
Step 102, judge whether human face region meets splicing condition, if so, then perform step 103; Otherwise, perform step 104.
Exemplary, described splicing condition specifically can be determined according to the facial image integrity degree comprised in human face region.Such as, the part face image-region 203 shown in Fig. 2 and face fringe region 201 can be considered to not meet splicing condition; And the whole facial image regions 202 shown in Fig. 2 can be considered to meet splicing condition.Splicing condition in the present embodiment can be adjusted according to practical situations and the effect that will reach by those skilled in the art, does not do concrete restriction at this.
Step 103, determine that present image is current image to be spliced, perform step 105.
Step 104, from present image, remove human face region, obtain current image to be spliced, perform step 105.
Exemplary, can by removing data division corresponding to human face region in data corresponding for present image, as pixel etc.
Step 105, current image to be spliced and stitching image to be spliced, form new stitching image.
Exemplary, the first two field picture obtained during pan-shot can be considered initial stitching image, when present image is the second two field picture, carry out above-mentioned human face region to the second two field picture judge and obtain current image to be spliced after process, be spliced in current image to be spliced in stitching image according to certain stitching algorithm with part not identical in stitching image, form new stitching image.Wherein, stitching algorithm can be identical with the stitching algorithm in existing distant view photograph connection scheme, and those skilled in the art all can realize, and repeat no more herein.When present image is the 3rd two field picture, the image that first two field picture and the second two field picture have spliced is as stitching image, carry out above-mentioned human face region to the 3rd two field picture equally judge and obtain current image to be spliced after process, by being spliced to part not identical in stitching image in current image to be spliced in stitching image, form new stitching image.Each two field picture afterwards the like, until by after last frame image mosaic, form final stitching image.Subsequently, also can carry out other post-processed such as noise elimination and toning, generate distant view photograph, and show on a display screen, check for user.
It should be noted that, it will be appreciated by those skilled in the art that, device for performing embodiment of the present invention method also can be integrated in be possessed in the terminal of image processing function, as desktop computer and notebook computer etc., for these terminals, the picture material (multiple pictures as taken continuously by camera copies in computer) for splicing can be imported in advance, then realize the splicing of distant view photograph by the method performing the embodiment of the present invention.
The joining method of the distant view photograph that the embodiment of the present invention one provides, the second two field picture obtained during pan-shot all can be considered present image to any one in last frame image, when recognize in present image comprise human face region time, judge whether human face region meets splicing condition, if do not meet, then from present image, remove human face region, obtain current image to be spliced; If meet, then determine that present image is current image to be spliced; Current image to be spliced and stitching image are spliced, forms new stitching image.By adopting technique scheme, successively the image except the first two field picture is spliced, when splicing, only aperture is merged the human face region of the condition of connecing, thus ensure that the facial image comprised in the distant view photograph be spliced into can not exist the distortion situations such as dislocation or distortion, meet the high-quality demand of user to facial image in distant view photograph, promote Consumer's Experience.
Embodiment two
The schematic flow sheet of the joining method of a kind of distant view photograph that Fig. 3 provides for the embodiment of the present invention two, the present embodiment is optimized based on above-described embodiment, in the present embodiment, is optimized the processing mode of the first two field picture and splicing condition.
Accordingly, the method for the present embodiment comprises the steps:
Step 301, judge whether the area of the human face region comprised in the first two field picture is not less than the area of the human face region comprised in the second two field picture, if so, then perform step 302; Otherwise, perform step 303.
Exemplary, when the terminal that user moves in hand from left to right carries out pan-shot, if there is the human face region comprising imperfect facial image in the right half part in the first two field picture, so along with the movement of terminal, the area of the human face region occurred in the second two field picture can be greater than the area of the human face region in the first two field picture, so can step 303 be performed, human face region in first two field picture is removed, as initial stitching image, because complete human face region will inevitably be there is in the second two field picture or the image that occurs below, complete human face region and stitching image are spliced, prevent facial image generation distortion, if there is the human face region comprising imperfect facial image in the left-half in the first two field picture, so along with the movement of terminal, the area of the human face region occurred in the second two field picture can be less than the area of the human face region in the first two field picture, so step 302 can be performed, directly determine that the first two field picture is initial stitching image, if contained the human face region of complete facial image in the first two field picture, the area of the human face region occurred in the second two field picture may equal the area of the human face region in the first two field picture, also can perform step 302.
Step 302, determine that the first two field picture is initial stitching image, perform step 304.
Step 303, the human face region removed in the first two field picture, obtain initial stitching image, performs step 304.
Exemplary, can by removing data division corresponding to human face region in data corresponding for present image, as pixel etc.
Step 304, when recognize in present image comprise human face region time, judge whether human face region meets splicing condition, if so, then perform step 305; Otherwise, perform step 306.
Exemplary, in this step, when judging whether the human face region in present image meets splicing condition, differentiated treatment can be carried out according to the difference of the frame number of present image number, specifically can comprise:
1, when described present image is any one in the second two field picture to two field picture second from the bottom, judge whether human face region is default complete human face region, if not, then determines not meet splicing condition; If so, then judge in stitching direction, whether the border of human face region is greater than predeterminable range value to the bee-line at present image edge, if be greater than, then determines to meet splicing condition, if be not more than, then determines not meet splicing condition; Wherein, stitching direction is the moving direction of camera when carrying out pan-shot.
Exemplary, the default complete human face region in the present embodiment comprises complete facial contour, and the area presetting complete human face region is greater than the area of complete facial contour.Such as, complete facial contour can be seen as ellipse, when identifying face, identifiable design goes out the size of facial contour, default complete human face region can be and has more the preset ratio value of facial contour width (as 20% in facial contour surrounding, this ratio value can adjust according to practical situations) region, the benefit of such setting is, the fringe region of facial contour may comprise the image section closely-related with face such as hair, cap and various ornaments, can ensure that the distortion phenomenons such as dislocation or distortion can not occur whole head image.
Exemplary, described predeterminable range value can be determined by the width in stitching direction presetting complete human face region.Such as, predeterminable range value is the preset ratio value of described width, such as 20% (this ratio value can adjust according to practical situations), when the width in stitching direction presetting complete human face region is the width of 140 pixels, predeterminable range value is 140 × 20%=28, i.e. the width of 28 pixels.
2, when described present image is last frame image, judge whether the area of the human face region comprised in last frame image is greater than the area of the facial image comprised in two field picture second from the bottom, if so, then determine to meet splicing condition; If not, then determine not meet splicing condition.
Exemplary, when the terminal that user moves in hand from left to right carries out pan-shot, if there is the human face region comprising imperfect facial image in the left-half in last frame image, so illustrate that the area of the human face region occurred in two field picture second from the bottom can be greater than the area of the human face region in last frame image, also complete facial image is there will be again in certain two field picture forward, so can step 306 be performed, human face region in last frame image is removed, as image to be spliced; If there is the human face region comprising imperfect facial image in the right half part in last frame image, so illustrate that the area of the human face region occurred in last frame image can be greater than the area of the human face region in two field picture second from the bottom, so step 305 can be performed, directly determine that last frame image is image to be spliced; If contain the human face region of complete facial image in last frame image, the area of the human face region occurred in two two field pictures reciprocal may equal the area of the human face region in last frame image, also can perform step 306.
In this step, generally speaking, processing mode for the face of same personage is, when the human face region first time comprising maximum face information of this personage occurs, this human face region is carried out retaining and participates in splicing, to guarantee that the distortion phenomenons such as dislocation and distortion do not occur the facial image of this personage.
Step 305, determine that present image is current image to be spliced, perform step 307.
Step 306, from present image, remove human face region, obtain current image to be spliced, perform step 307.
Step 307, current image to be spliced and stitching image to be spliced, form new stitching image.
The embodiment of the present invention two, on the basis of embodiment one, has been described in detail splicing condition, and takes different processing modes to the first two field picture and last frame image, can guarantee the integrality of whole distant view photograph.
Embodiment three
The schematic flow sheet of the joining method of a kind of preferred distant view photograph that Fig. 4 provides for the embodiment of the present invention three.As shown in Figure 4, the method comprises:
Step 401, judge whether the area of the human face region comprised in the first two field picture is not less than the area of the human face region comprised in the second two field picture, if so, then perform step 402; Otherwise, perform step 403.
Exemplary, in this step, if when not comprising human face region in the first two field picture, can be considered that the area of human face region is 0.
Step 402, determine that the first two field picture is initial stitching image, perform step 404.
Step 403, the human face region removed in the first two field picture, obtain initial stitching image, performs step 404.
Whether comprise human face region in step 404, identification present image, if so, then perform step 405; Otherwise, perform step 406.
Wherein, present image is any one in the second two field picture to two field picture second from the bottom.When first time performs this step, described present image is the second two field picture.
Step 405, judge whether the human face region comprised in present image meets splicing condition, if so, then perform step 406; Otherwise, perform step 407.
In the present embodiment, can judge whether human face region is default complete human face region, if not, then determines not meet splicing condition; If so, then judge in stitching direction, whether the border of human face region is greater than predeterminable range value to the bee-line at present image edge, if be greater than, then determines to meet splicing condition, if be not more than, then determines not meet splicing condition.Wherein, stitching direction is the moving direction of camera when carrying out pan-shot.
Presetting complete human face region is have more 20% of facial contour width in facial contour surrounding.Such as, in units of pixel, when recognizing the region that facial contour is 100 × 100, the length of side so presetting complete human face region is (100 × 20%)+100+ (100 × 20%), and namely presetting complete human face region is 140 × 140.
Predeterminable range value is 20% of the width in stitching direction of default complete human face region, and as above-mentioned citing, predeterminable range value is 140 × 20%=28, i.e. the width of 28 pixels.
Exemplary, if the human face region in present image is 140 × 60, then do not meet splicing condition; If the human face region in present image is 140 × 140, but its border in stitching direction was 20 (being less than 28) to the bee-line at present image edge, did not so meet splicing condition.
Step 406, determine that present image is current image to be spliced, perform step 408.
Step 407, from present image, remove human face region, obtain current image to be spliced, perform step 408.
Exemplary, from present image, remove the human face region not meeting splicing condition, as the human face region of 140 × 60 of above-mentioned citing, obtain current image to be spliced.
Step 408, current image to be spliced and stitching image to be spliced, form new stitching image.
Exemplary, when human face region in present image meets splicing condition, at least one two field picture before can get rid of when splicing the region not meeting splicing condition, as the human face region of 140 × 60, in present image 150 × 150 (having more certain distance in default complete human face region surrounding) human face region and stitching image can be spliced, when guaranteeing image mosaic, there will not be space.May shake due to during the terminal of user in mobile hand, the human face region not meeting splicing condition so removed may not be in the same horizontal line, after splicing, sawtooth or curve may be there is in the boundary after removing human face region, when the human face region meeting splicing condition being used for splicing is set to be a bit larger tham default complete human face region, sufficient image section can be ensured to make up above-mentioned defect, avoid occurring space.
Whether step 409, the next frame image judging present image are last frame image, if so, then perform step 410; Otherwise, using the next frame image of present image as new present image, and return execution step 404.
Step 410, judge whether the area of the human face region comprised in last frame image is greater than the area of the facial image comprised in two field picture second from the bottom, if so, then perform step 411; Otherwise, perform step 412.
Exemplary, in this step, if when not comprising human face region in last frame image, can be considered that the area of human face region is 0.
Step 411, last frame image and stitching image to be spliced, form final stitching image.
Step 412, the human face region removed in last frame image, and splice with stitching image, form final stitching image.
The joining method of the preferred distant view photograph that the embodiment of the present invention three provides, after first two field picture of user's splicing is judged, determine initial stitching image, then successively image is afterwards spliced, when splicing, only aperture is merged the human face region of the condition of connecing, when ensureing that the facial image comprised in the distant view photograph be spliced into can not exist the distortion phenomenons such as dislocation or distortion, ensure the integrality of facial image in the first two field picture and last frame image, meet the high-quality demand of user to facial image in distant view photograph to greatest extent, promote Consumer's Experience.
Embodiment four
The structured flowchart of the splicing apparatus of a kind of distant view photograph that Fig. 5 provides for the embodiment of the present invention four, this device can by software and/or hardware implementing, and generally in the terminal integrated, the joining method method by execution distant view photograph carrys out spliced panoramic photo.As shown in Figure 5, this device comprises: current image determination module 501 to be spliced and concatenation module 502.
Wherein, current image determination module 501 to be spliced, for when recognize in present image comprise human face region time, judge whether described human face region meets splicing condition, if do not meet, then from described present image, remove described human face region, obtain current image to be spliced; If meet, then determine that described present image is current image to be spliced; Concatenation module 502, for described current image to be spliced and stitching image being spliced, forms new stitching image; Wherein, the second two field picture obtained when described present image is pan-shot is to any one in last frame image.
On the basis of above-described embodiment, this device also can comprise: stitching image determination module, for recognize in present image comprise human face region time, before judging whether described human face region meets splicing condition, judge whether the area of the human face region comprised in the first two field picture is not less than the area of the human face region comprised in the second two field picture, if so, then determine that described first two field picture is initial stitching image; If not, then remove the human face region in described first two field picture, obtain initial stitching image.
On the basis of above-described embodiment, described current image determination module to be spliced, can comprise splicing condition judgment unit, for:
When described present image is any one in the second two field picture to two field picture second from the bottom, judges whether described human face region is default complete human face region, if not, then determine not meet described splicing condition; If so, then judge in stitching direction, whether the border of described human face region is greater than predeterminable range value to the bee-line at described present image edge, if be greater than, then determines to meet described splicing condition, if be not more than, then determines not meet described splicing condition;
When described present image is last frame image, judges whether the area of the human face region comprised in described last frame image is greater than the area of the facial image comprised in two field picture second from the bottom, if so, then determine to meet splicing condition; If not, then determine not meet splicing condition;
Wherein, described stitching direction is the moving direction of camera when carrying out pan-shot.
On the basis of above-described embodiment, described default complete human face region comprises complete facial contour, and the described area presetting complete human face region is greater than the area of described complete facial contour.
On the basis of above-described embodiment, described predeterminable range value is determined by the described width in stitching direction presetting complete human face region.
The said goods can perform the method that any embodiment of the present invention provides, and possesses the corresponding functional module of manner of execution and beneficial effect.The not ins and outs of detailed description in the present embodiment, the method that can provide see any embodiment of the present invention.
Note, above are only preferred embodiment of the present invention and institute's application technology principle.Skilled person in the art will appreciate that and the invention is not restricted to specific embodiment described here, various obvious change can be carried out for a person skilled in the art, readjust and substitute and can not protection scope of the present invention be departed from.Therefore, although be described in further detail invention has been by above embodiment, the present invention is not limited only to above embodiment, when not departing from the present invention's design, can also comprise other Equivalent embodiments more, and scope of the present invention is determined by appended right.
Claims (10)
1. a joining method for distant view photograph, is characterized in that, comprising:
When recognize in present image comprise human face region time, judge whether described human face region meets splicing condition, if do not meet, then from described present image, remove described human face region, obtain current image to be spliced; If meet, then determine that described present image is current image to be spliced;
Described current image to be spliced and stitching image are spliced, forms new stitching image;
Wherein, the second two field picture obtained when described present image is pan-shot is to any one in last frame image.
2. method according to claim 1, is characterized in that, recognize in present image comprise human face region time, before judging whether described human face region meets splicing condition, also comprise:
Judge whether the area of the human face region comprised in the first two field picture is not less than the area of the human face region comprised in the second two field picture, if so, then determine that described first two field picture is initial stitching image; If not, then remove the human face region in described first two field picture, obtain initial stitching image.
3. method according to claim 2, is characterized in that, describedly judges whether described human face region meets splicing condition, comprising:
When described present image is any one in the second two field picture to two field picture second from the bottom, judge whether described human face region is default complete human face region, if not, then determines not meet splicing condition; If so, then judge in stitching direction, whether the border of described human face region is greater than predeterminable range value to the bee-line at described present image edge, if be greater than, then determines to meet splicing condition, if be not more than, then determines not meet splicing condition;
When described present image is last frame image, judges whether the area of the human face region comprised in described last frame image is greater than the area of the facial image comprised in two field picture second from the bottom, if so, then determine to meet splicing condition; If not, then determine not meet splicing condition;
Wherein, described stitching direction is the moving direction of camera when carrying out pan-shot.
4. method according to claim 3, is characterized in that, described default complete human face region comprises complete facial contour, and the described area presetting complete human face region is greater than the area of described complete facial contour.
5. method according to claim 3, is characterized in that, described predeterminable range value is determined by the described width in stitching direction presetting complete human face region.
6. a splicing apparatus for distant view photograph, is characterized in that, comprising:
Current image determination module to be spliced, for when recognize in present image comprise human face region time, judge whether described human face region meets splicing condition, if do not meet, then from described present image, remove described human face region, obtain current image to be spliced; If meet, then determine that described present image is current image to be spliced;
Concatenation module, for described current image to be spliced and stitching image being spliced, forms new stitching image;
Wherein, the second two field picture obtained when described present image is pan-shot is to any one in last frame image.
7. device according to claim 6, is characterized in that, also comprises:
Stitching image determination module, for recognize in present image comprise human face region time, before judging whether described human face region meets splicing condition, judge whether the area of the human face region comprised in the first two field picture is not less than the area of the human face region comprised in the second two field picture, if so, then determine that described first two field picture is initial stitching image; If not, then remove the human face region in described first two field picture, obtain initial stitching image.
8. device according to claim 7, is characterized in that, described current image determination module to be spliced, comprises splicing condition judgment unit, for:
When described present image is any one in the second two field picture to two field picture second from the bottom, judges whether described human face region is default complete human face region, if not, then determine not meet described splicing condition; If so, then judge in stitching direction, whether the border of described human face region is greater than predeterminable range value to the bee-line at described present image edge, if be greater than, then determines to meet described splicing condition, if be not more than, then determines not meet described splicing condition;
When described present image is last frame image, judges whether the area of the human face region comprised in described last frame image is greater than the area of the facial image comprised in two field picture second from the bottom, if so, then determine to meet splicing condition; If not, then determine not meet splicing condition;
Wherein, described stitching direction is the moving direction of camera when carrying out pan-shot.
9. device according to claim 8, is characterized in that, described default complete human face region comprises complete facial contour, and the described area presetting complete human face region is greater than the area of described complete facial contour.
10. device according to claim 8, is characterized in that, described predeterminable range value is determined by the described width in stitching direction presetting complete human face region.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510585372.XA CN105139340B (en) | 2015-09-15 | 2015-09-15 | A kind of joining method and device of distant view photograph |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510585372.XA CN105139340B (en) | 2015-09-15 | 2015-09-15 | A kind of joining method and device of distant view photograph |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105139340A true CN105139340A (en) | 2015-12-09 |
| CN105139340B CN105139340B (en) | 2019-02-19 |
Family
ID=54724673
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510585372.XA Expired - Fee Related CN105139340B (en) | 2015-09-15 | 2015-09-15 | A kind of joining method and device of distant view photograph |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105139340B (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107172442A (en) * | 2017-06-11 | 2017-09-15 | 成都吱吖科技有限公司 | A kind of interactive panoramic video storage method and device based on virtual reality |
| WO2018072087A1 (en) * | 2016-10-18 | 2018-04-26 | 华为技术有限公司 | Method for realizing effect of photo being taken by others through selfie, and photographing device |
| CN108898171A (en) * | 2018-06-20 | 2018-11-27 | 深圳市易成自动驾驶技术有限公司 | Recognition processing method, system and computer readable storage medium |
| CN110738078A (en) * | 2018-07-19 | 2020-01-31 | 青岛海信移动通信技术股份有限公司 | face recognition method and terminal equipment |
| WO2021179923A1 (en) * | 2020-03-13 | 2021-09-16 | 深圳看到科技有限公司 | User facial image display method and display device and corresponding storage medium |
| CN117218109A (en) * | 2023-10-16 | 2023-12-12 | 北京卓视智通科技有限责任公司 | Vehicle lateral mosaic image integrity detection method, system, equipment and medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120263397A1 (en) * | 2011-04-12 | 2012-10-18 | Sony Corporation | Image processing device, image processing method, and program |
| CN103534726A (en) * | 2011-05-17 | 2014-01-22 | 苹果公司 | Positional sensor-assisted image registration for panoramic photography |
| CN104601880A (en) * | 2014-12-11 | 2015-05-06 | 广东欧珀移动通信有限公司 | Method for generating panoramic photo and mobile terminal |
-
2015
- 2015-09-15 CN CN201510585372.XA patent/CN105139340B/en not_active Expired - Fee Related
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120263397A1 (en) * | 2011-04-12 | 2012-10-18 | Sony Corporation | Image processing device, image processing method, and program |
| CN103534726A (en) * | 2011-05-17 | 2014-01-22 | 苹果公司 | Positional sensor-assisted image registration for panoramic photography |
| CN104601880A (en) * | 2014-12-11 | 2015-05-06 | 广东欧珀移动通信有限公司 | Method for generating panoramic photo and mobile terminal |
Cited By (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2018072087A1 (en) * | 2016-10-18 | 2018-04-26 | 华为技术有限公司 | Method for realizing effect of photo being taken by others through selfie, and photographing device |
| US10917559B2 (en) | 2016-10-18 | 2021-02-09 | Huawei Technologies Co., Ltd. | Method for achieving non-selfie-taking effect through selfie-taking and photographing device |
| CN107172442A (en) * | 2017-06-11 | 2017-09-15 | 成都吱吖科技有限公司 | A kind of interactive panoramic video storage method and device based on virtual reality |
| CN108898171A (en) * | 2018-06-20 | 2018-11-27 | 深圳市易成自动驾驶技术有限公司 | Recognition processing method, system and computer readable storage medium |
| CN108898171B (en) * | 2018-06-20 | 2022-07-22 | 深圳市易成自动驾驶技术有限公司 | Image recognition processing method, system and computer readable storage medium |
| CN110738078A (en) * | 2018-07-19 | 2020-01-31 | 青岛海信移动通信技术股份有限公司 | face recognition method and terminal equipment |
| WO2021179923A1 (en) * | 2020-03-13 | 2021-09-16 | 深圳看到科技有限公司 | User facial image display method and display device and corresponding storage medium |
| CN117218109A (en) * | 2023-10-16 | 2023-12-12 | 北京卓视智通科技有限责任公司 | Vehicle lateral mosaic image integrity detection method, system, equipment and medium |
| CN117218109B (en) * | 2023-10-16 | 2024-08-20 | 北京卓视智通科技有限责任公司 | Vehicle lateral mosaic image integrity detection method, system, equipment and medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105139340B (en) | 2019-02-19 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105139340A (en) | Method and device for splicing panoramic photos | |
| US10452945B2 (en) | Image generating device, electronic device, image generating method and recording medium | |
| US9350924B2 (en) | Portable electronic devices with integrated image/video compositing | |
| CN105100615B (en) | A kind of method for previewing of image, device and terminal | |
| US9325899B1 (en) | Image capturing device and digital zooming method thereof | |
| EP2881913A1 (en) | Image splicing method and apparatus | |
| US8619148B1 (en) | Image correction after combining images from multiple cameras | |
| WO2018176925A1 (en) | Hdr image generation method and apparatus | |
| EP1870854A2 (en) | Apparatus and method for panoramic photography in portable terminal | |
| WO2013145799A1 (en) | Image processing device, photographing device, program, and image processing method | |
| KR20130112574A (en) | Apparatus and method for improving quality of enlarged image | |
| US20090295787A1 (en) | Methods for Displaying Objects of Interest on a Digital Display Device | |
| WO2015161561A1 (en) | Method and device for terminal to achieve image synthesis based on multiple cameras | |
| TW200926062A (en) | Image generation method and apparatus, program therefor, and storage medium for storing the program | |
| CN105247567B (en) | A kind of image focusing device, method, system and non-transient program storage device again | |
| CN103024271A (en) | Method photographing on electronic device and electronic device adopting method | |
| CN112930677B (en) | Method for switching between first lens and second lens and electronic device | |
| CN109690568A (en) | A kind of processing method and mobile device | |
| CN104270571B (en) | Image processing method and electronic equipment | |
| CN105530425A (en) | Automatic continuous shooting system | |
| CN108810326B (en) | Photographing method and device and mobile terminal | |
| CN112529778B (en) | Image stitching method and device of multi-camera equipment, storage medium and terminal | |
| CN103366351B (en) | Produce method and the image acquiring device thereof of panoramic picture | |
| CN109218602B (en) | Image acquisition device, image processing method and electronic device | |
| US9602708B2 (en) | Rectified stereoscopic 3D panoramic picture |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Applicant after: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. Address before: 523860 No. 18, Wu Sha Beach Road, Changan Town, Dongguan, Guangdong Applicant before: GUANGDONG OPPO MOBILE TELECOMMUNICATIONS Corp.,Ltd. |
|
| CB02 | Change of applicant information | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20190219 |
|
| CF01 | Termination of patent right due to non-payment of annual fee |